1310Accesses
30Citations
Abstract
In this paper, an unsupervised co-segmentation algorithm is proposed, which can be applied to the image with multiple foreground objects simultaneously and the background changes dramatically. The color edge image in RGB space is extracted for semantic extraction. This method can effectively distinguish foreground and background by recursively modeling the appearance distribution of pixels and regions. The coherence of image foreground and background model is enhanced by using the correlation between different image regions and image interior. Experimental results show that deep convolutional neural network can effectively realize semantic classification of scene images by end-to-end feature learning and achieve accurate semantic segmentation of scene images.
This is a preview of subscription content,log in via an institution to check access.
Access this article
Subscribe and save
- Get 10 units per month
- Download Article/Chapter or eBook
- 1 Unit = 1 Article or 1 Chapter
- Cancel anytime
Buy Now
Price includes VAT (Japan)
Instant access to the full article PDF.




Similar content being viewed by others
Explore related subjects
Discover the latest articles and news from researchers in related subjects, suggested using machine learning.Change history
12 December 2022
This article has been retracted. Please see the Retraction Notice for more detail:https://doi.org/10.1007/s00521-022-08146-9
References
Kumar M, Mao YH, Wang YH, Qiu TR, Yang C, Zhang WP (2017) Fuzzy theoretic approach to signals and systems: static systems. Inf Sci 418-419:668–702
Zhang WP, Yang JZ, Fang YL, Chen HY, Mao YH, Kumar M (2017) Analytical fuzzy approach to biological data analysis. Saudi J Biol Sci 24(3):563–573
Wang S, Wang M, Zhao X et al (2018) Two-stage object detection based on deep pruning for remote sensing image. In: International conference on knowledge science, engineering and management. Springer, Cham, pp 137–147
Suh HP, Kim Y, Suh Y et al (2018) Multidetector computed tomography (CT) analysis of 168 cases in diabetic patients with total superficial femoral artery occlusion: is it safe to use an anterolateral thigh flap without CT angiography in diabetic patients. J Reconstr Microsurg 34(01):065–070
Yuan C, Xia Z, Jiang L (2019) Fingerprint liveness detection using an improved CNN with image scale equalization. IEEE Access 7(99):26953–26966
Vijayan M, Ramasundaram M (2018) Moving object detection using vector image model. Optik 168:963–973
Wei P, Ball JE, Anderson DT (2018) Fusion of an ensemble of augmented image detectors for robust object detection. Sensors 18(3):894
Royer E, Bouchara F (2018) Guiding text image keypoints extraction through layout analysis. In: IAPR international conference on document analysis and recognition. IEEE, pp 9–14
Minaee S, Wang Y (2018) Text extraction from texture images using masked signal decomposition. In: IEEE global conference on signal and information processing. IEEE, pp 1210–1214
Vasilopoulos N, Wasfi Y, Kavallieratou E (2018) Automatic text extraction from arabic newspapers. In: International conference image analysis and recognition. Springer, Cham, pp 505–510
Bai D, Wang C, Bo Z (2018) CNN feature boosted SeqSLAM for real-time loop closure detection. Chin J Electron 27(3):488–499
Liang F, Shen C, Wu F (2018) An iterative BP-CNN architecture for channel decoding. IEEE J Sel Top Signal Process 12(1):144–159
Huan Du, Liu Zhi, Song Hangke, Mei Lin, Zheng Xu (2016) Improving RGBD saliency detection using progressive region classification and saliency fusion. IEEE Access 4:8987–8994
Dai D, Sakaridis C, Hecker S (2019) Curriculum model adaptation with synthetic and real data for semantic foggy scene understanding. Int J Comput Vision 11:1–23
Zhang C, Pan X, Hl Li (2018) A hybrid MLP-CNN classifier for very fine resolution remotely sensed image classification. ISPRS J Photogram Rem Sens 140:133–144
Khatami A, Babaie M, Tizhoosh HR (2010) A sequential search-space shrinking using CNN transfer learning and a radon projection pool for medical image retrieval. Expert Syst Appl 100:224–233
Tama BA, Rhee K-H (2019) An in-depth experimental study of anomaly detection using gradient boosted machine. Neural Comput Appl 31(4):955–965
Yokota F, Otake Y, Takao M (2018) Automated muscle segmentation from CT images of the hip and thigh using a hierarchical multi-atlas method. Int J Comput Assist Radiol Surg 13(9):1–10
Keun CH, Seop KH, Ho JS (2012) Sonography of affected and unaffected shoulders in hemiplegic patients: analysis of the relationship between sonographic imaging data and clinical variables. Ann Rehabil Med 36(6):828–835
Dutta A, Zhong Y, Depraetere B (2014) Model-based and model-free learning strategies for wet clutch control. Mechatronics 24(8):1008–1020
Kim S, Ji Y, Lee KB (2018) An effective sign language learning with object detection based ROI segmentation. In: IEEE international conference on robotic computing. IEEE Computer Society, pp 330–333
Wang K, Liang L, Yan X (2018) Cost-effective object detection: active sample mining with switchable selection criteria. IEEE Trans Neural Netw Learn Syst 99:1–17
Khanzadeh T, Hagh MF, Talebi M (2018) Investigation ofBAXandBCL2expression and apoptosis in a resveratrol- and prednisolone-treated human T-ALL cell line, CCRF-CEM. Blood Res 53(1):53–60
Fei Y, Wang KCP, Zhang A (2019) Pixel-level cracking detection on 3D asphalt pavement images through deep-learning-based CrackNet-V. IEEE Trans Intell Transp Syst 99:1–12
Kim Y, Kang BN, Kim D (2018) Detector with focus: normalizing gradient in image pyramid. In: IEEE international conference on image processing. IEEE, pp 420–424
Liang Y, Zhang Y, Chen Z (2019) Re-nucleation and etching of graphene during the cooling stage of chemical vapor deposition. J Electron Mater 48(3):1740–1745
Glasner D, Galun M, Alpert S (2012) Viewpoint-aware object detection and continuous pose estimation. Image Vis Comput 30(12):923–933
Kang MS, Lim YC (2018) High performance and fast object detection in road environments. In: Seventh international conference on image processing theory, TOOLS and applications. IEEE, pp 1–6
Furuta R, Tsubaki I, Yamasaki T (2018) Fast volume seam carving with multipass dynamic programming. IEEE Trans Circuits Syst Video Technol 28(5):1087–1101
Acknowledgements
This work was supported by the Natural Science Foundation of Shandong Province (No. ZR2015FL007), National Natural Science Foundation of China (Nos. 61703192 and 61603171) and the Fundamental Research Funds for the Central Universities (2018CDXYTX0010).
Author information
Authors and Affiliations
School of Mechanical and Automotive Engineering, Liaocheng University, Liaocheng, Shandong, China
Laigang Zhang, Qun Sun, Ying Zhao & Deying Feng
School of Management, Wuhan Donghu University, Wuhan, China
Zhou Sheng
Shandong University, Jinan, Shandong, China
Yibin Li
- Laigang Zhang
Search author on:PubMed Google Scholar
- Zhou Sheng
Search author on:PubMed Google Scholar
- Yibin Li
Search author on:PubMed Google Scholar
- Qun Sun
Search author on:PubMed Google Scholar
- Ying Zhao
Search author on:PubMed Google Scholar
- Deying Feng
Search author on:PubMed Google Scholar
Corresponding author
Correspondence toZhou Sheng.
Ethics declarations
Conflict of interest
There are no conflicts of interests in this work.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
This article has been retracted. Please see the retraction notice for more detail:https://doi.org/10.1007/s00521-022-08146-9
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Zhang, L., Sheng, Z., Li, Y.et al. RETRACTED ARTICLE: Image object detection and semantic segmentation based on convolutional neural network.Neural Comput & Applic32, 1949–1958 (2020). https://doi.org/10.1007/s00521-019-04491-4
Received:
Accepted:
Published:
Issue Date:
Share this article
Anyone you share the following link with will be able to read this content:
Sorry, a shareable link is not currently available for this article.
Provided by the Springer Nature SharedIt content-sharing initiative